TELE 6500 — Machine Learning for IoT Systems
4 semester hoursGraduateLectureusually offered: fall, springtypical days: TBostonTraditional
Studies the design, development, rollout, and maintenance of machine learning algorithms for IoT systems, which generate and process time series data under memory and timeliness constraints. Focuses on verticals like Industry 4.0, wearables, and smart grids/homes. Explores the nuances of handling IoT time series data in both edge and cloud computing settings including the preparation, exploration, and feature engineering for sensor data. Covers domain-specific problem classes like forecasting, change point detection, and temporal anomaly detection. Addresses customized performance metrics for time series algorithms. Analyzes deep learning architectures for time series problems using TinyML for embedded devices. Course projects focus on time series, going beyond traditional datasets used in conventional ML classes.
Offering history
| Term | Sections | Enrolled | Capacity | Full | Open seats/section |
|---|---|---|---|---|---|
| Fall 2024 | 1 | 8 | 30 | 27% | 22.0 |
| Spring 2025 | 1 | 6 | 21 | 29% | 15.0 |
| Fall 2025 | 1 | 3 | 30 | 10% | 27.0 |
| Spring 2026 | 1 | 4 | 40 | 10% | 36.0 |
Snapshots from scheduled scrapes — not live seat availability. "Full" can exceed 100% when sections over-enroll.
Meeting times
Share of recent sections by weekday: M 0% · T 81% · W 0% · Th 19% · F 0%
Common patterns: T (81% of sections), R (19% of sections) — in patterns, R means Thursday
Professors
Fall
- Abhishek Murthy (100% of students) · reviews
Spring
- Abhishek Murthy (100% of students) · reviews
Percentages are each professor's average share of the season's enrolled students in recent terms.
Links
Official catalog (TELE course descriptions) · Student reviews on RateMyHusky · All TELE courses · Plan it at numap.app